© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 9387
    Prev
    Next
    INDEX
    Explanations

    adverbs denoting degree or intensity

    oai_token-act-pair · gpt-3.5-turbo

    quantifiers and modifiers indicating degree or extent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ö¼
    -0.69
     annexed
    -0.54
     eruption
    -0.50
     Pwr
    -0.50
     unveiling
    -0.50
     Seat
    -0.50
     Williamson
    -0.50
     Editorial
    -0.50
    liest
    -0.50
     Anat
    -0.50
    POSITIVE LOGITS
    izont
    0.88
    orously
    0.79
    onto
    0.75
    anes
    0.71
    isively
    0.66
    thin
    0.66
    enough
    0.66
    eper
    0.66
    ween
    0.65
    actively
    0.64
    Activations Density 0.480%

    No Known Activations